Text Classification Model Based on fastText

Yao, Tengjun; Zhai, Zhengang; Gao, Bingtao

doi:10.1109/icaiis49377.2020.9194939

Cited by 38 publications

(14 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the dataset's extensive vocabulary, all the previously mentioned text transformation techniques generate large vectors. These large vectors can lead to the curse of dimensionality when used with machine learning models [43]. To tackle this issue, we employed Principal Component Analysis (PCA) [44] to summarize and reduce the dimensionality of the text representations.…”

Section: Text Transformationmentioning

confidence: 99%

“Paper, Meet Code”: A Deep Learning Approach to Linking Scholarly Articles With GitHub Repositories

Puangjaktha,

Choetkiertikul,

Tuarob

2024

IEEE Access

View full text Add to dashboard Cite

Computer scientists often publish their source code accompanying their publications, prominently using code repositories across various domains. Despite the concurrent existence of scholarly articles and their associated official code repositories, explicit references linking the two are often missing. Traditionally, identifying whether scholarly content and code repositories pertain to the same research project requires manual inspection, a time-consuming task. This paper proposes a deep learning-based algorithm for automatically matching scholarly articles with their corresponding official code repositories. Our findings indicate that the most common linking information includes the paper title and BibTeX entries, typically found in the repository's readme document. In this study, we employed SPECTER for vector embedding of paper and repository metadata. Utilizing these embedding representations with the Light Gradient Boosting Machine (LGBM), our method achieved an F1 score of 0.94. Moreover, combining our best model with a rule-based approach improved performance by 5.31%. This study successfully delineates a connection between academic papers and associated official code repositories, minimizing reliance on explicit bibliographic information in repositories.

show abstract

Section: Text Transformationmentioning

confidence: 99%

“Paper, Meet Code”: A Deep Learning Approach to Linking Scholarly Articles With GitHub Repositories

Puangjaktha,

Choetkiertikul,

Tuarob

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Web of science dataset is used for classification [7]. Fast text algorithm is used for the classification of text in Research article [8]. The classification is performed with Recurrent Neural Network (RNN) [9].…”

Section: Related Workmentioning

confidence: 99%

SF-CNN: Deep Text Classification and Retrieval for Text Documents

Sarasu¹,

Thyagharajan²,

Shanker³

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

“…The advantage of this type of model is that it is simple and effective, but the disadvantage is that it needs to use manual feature engineering to extract feature vectors, which is time-consuming and has poor scalability. With the development of deep learning technology, scholars have proposed advanced classification models such as FastText [15], CNN [16], RNN [17] and their series of variants and have achieved good classification results. The advantage of the deep learning model is that it can accurately predict the text category by combining the distributed word vector representation technology with the deep neural network.…”

Section: Related Workmentioning

confidence: 99%

“…Avg Accuracy (%) Min-Loss Avg F 1 -Score (%) TF-IDF [23] 89.26 -85 Naive Bayes [14] 90.13 -90 SVM [13] 92.39 -91 FastText [15] 92.24 -92 LSTM [24] 93.17 0.22 93 RNN [17] 94.49 0.21 94 TextGCN [25] 92.78 0.24 92 CNN [16] 96.26 0.13…”

Section: Model Namementioning

confidence: 99%

Chinese News Text Classification Method via Key Feature Enhancement

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

(1) Background: Chinese news text is a popular form of media communication, which can be seen everywhere in China. Chinese news text classification is an important direction in natural language processing (NLP). How to use high-quality text classification technology to help humans to efficiently organize and manage the massive amount of web news is an urgent problem to be solved. It is noted that the existing deep learning methods rely on a large-scale tagged corpus for news text classification tasks and this model is poorly interpretable because the size is large. (2) Methods: To solve the above problems, this paper proposes a Chinese news text classification method based on key feature enhancement named KFE-CNN. It can effectively expand the semantic information of key features to enhance sample data and then combine the zero–one binary vector representation to transform text features into binary vectors and input them into CNN model for training and implementation, thus improving the interpretability of the model and effectively compressing the size of the model. (3) Results: The experimental results show that our method can significantly improve the overall performance of the model and the average accuracy and F1-score of the THUCNews subset of the public dataset reached 97.84% and 98%. (4) Conclusions: this fully proved the effectiveness of the KFE-CNN method for the Chinese news text classification task and it also fully demonstrates that key feature enhancement can improve classification performance.

show abstract

Text Classification Model Based on fastText

Cited by 38 publications

References 1 publication

“Paper, Meet Code”: A Deep Learning Approach to Linking Scholarly Articles With GitHub Repositories

“Paper, Meet Code”: A Deep Learning Approach to Linking Scholarly Articles With GitHub Repositories

SF-CNN: Deep Text Classification and Retrieval for Text Documents

Chinese News Text Classification Method via Key Feature Enhancement

Contact Info

Product

Resources

About